Towards AI Agents Supported Research Problem Formulation

2025-12-14

AI Summary

Software engineering research often suffers from low practical relevance due to problem formulations that diverge from industrial practice. Method: This paper introduces the first collaborative framework that systematically integrates AI agents into the early-stage research question formulation process, grounded in Lean Research Inception (LRI). The framework supports pre-populated problem attributes, alignment between academic and industrial perspectives, research question refinement, multi-stakeholder evaluation simulation, and decision support—enhanced by context-awareness anchored in real-world industrial practice to foster cross-role collaboration and critical reflection. Contribution/Results: Descriptive evaluation indicates that AI agents significantly improve the quality of collaborative discussions and deepen critical scrutiny across three dimensions: value, feasibility, and applicability of research questions. The framework has received preliminary recognition from the academic community; however, empirical validation remains pending.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Humans and AI: Human-AI Collaboration / Human-AI Teaming
• Multiagent Systems: Modeling other Agents

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Economics, Online Markets and Human Computation: Research challenges in human and human-AI computation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Poorly formulated research problems can compromise the practical relevance of Software Engineering studies by not reflecting the complexities of industrial practice. This vision paper explores the use of artificial intelligence agents to support SE researchers during the early stage of a research project, the formulation of the research problem. Based on the Lean Research Inception framework and using a published study on code maintainability in machine learning as a reference, we developed a descriptive evaluation of a scenario illustrating how AI agents, integrated into LRI, can support SE researchers by pre filling problem attributes, aligning stakeholder perspectives, refining research questions, simulating multiperspective assessments, and supporting decision making. The descriptive evaluation of the scenario suggests that AI agent support can enrich collaborative discussions and enhance critical reflection on the value, feasibility, and applicability of the research problem. Although the vision of integrating AI agents into LRI was perceived as promising to support the context aware and practice oriented formulation of research problems, empirical validation is needed to confirm and refine the integration of AI agents into problem formulation.

Problem

• AI agents support research problem formulation in Software Engineering
• They align stakeholder perspectives and refine research questions
• They enhance critical reflection on research value and feasibility

Innovation

• AI agents integrated into Lean Research Inception framework
• AI agents pre-fill problem attributes and align stakeholder perspectives
• AI agents simulate multiperspective assessments to support decision making